2018
Aguilar, Gustavo; Monroy, A. Pastor López; Gonzalez, Fabio A.; Solorio, Thamar
Modeling Noisiness to Recognize Named Entities using Multitask Neural Networks on Social Media Inproceedings
In: for Computational Linguistics, Association (Ed.): Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Association for Computational Linguistics, New Orleans, Louisiana, 2018.
Abstract | Links | BibTeX | Tags: CRF, Multitask, NER, Phonetics, Phonology, Social Media
@inproceedings{gaguilar2018,
title = {Modeling Noisiness to Recognize Named Entities using Multitask Neural Networks on Social Media},
author = {Gustavo Aguilar and A. Pastor López Monroy and Fabio A. Gonzalez and Thamar Solorio},
editor = {Association for Computational Linguistics },
url = {http://www.aclweb.org/anthology/N18-1127},
year = {2018},
date = {2018-06-01},
booktitle = {Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies},
publisher = {Association for Computational Linguistics},
address = {New Orleans, Louisiana},
abstract = {Recognizing named entities in a document is a key task in many NLP applications. Although current state-of-the-art approaches to this task reach a high performance on clean text (e.g. newswire genres), those algorithms dramatically degrade when they are moved to noisy environments such as social media domains. We present two systems that address the challenges of processing social media data using character-level phonetics and phonology, word embeddings, and Part-of-Speech tags as features. The first model is a multitask end-to-end Bidirectional Long Short-Term Memory (BLSTM)-Conditional Random Field (CRF) network whose output layer contains two CRF classifiers. The second model uses a multitask BLSTM network as feature extractor that transfers the learning to a CRF classifier for the final prediction. Our systems outperform the current F1 scores from state-of-the-art on the Workshop on Noisy User-generated Text 2017 dataset by 2.45% and 3.69%, establishing a more suitable approach for social media environments. },
keywords = {CRF, Multitask, NER, Phonetics, Phonology, Social Media},
pubstate = {published},
tppubtype = {inproceedings}
}
Recognizing named entities in a document is a key task in many NLP applications. Although current state-of-the-art approaches to this task reach a high performance on clean text (e.g. newswire genres), those algorithms dramatically degrade when they are moved to noisy environments such as social media domains. We present two systems that address the challenges of processing social media data using character-level phonetics and phonology, word embeddings, and Part-of-Speech tags as features. The first model is a multitask end-to-end Bidirectional Long Short-Term Memory (BLSTM)-Conditional Random Field (CRF) network whose output layer contains two CRF classifiers. The second model uses a multitask BLSTM network as feature extractor that transfers the learning to a CRF classifier for the final prediction. Our systems outperform the current F1 scores from state-of-the-art on the Workshop on Noisy User-generated Text 2017 dataset by 2.45% and 3.69%, establishing a more suitable approach for social media environments.